search

jcwleo / random-network-distillation-pytorch

Random Network Distillation pytorch
MIT License
241 stars 43 forks source link

About sticky action #30

Open tongzhoumu opened 5 years ago

tongzhoumu commented 5 years ago

Hi,

In your code (envs.py), I saw that you first use MaxAndSkipEnv() to wrap the environment, and then apply the sticky action. However, in RND's author's code, I found that they first wrap the env by StickyActionEnv(), then wrap it by MaxAndSkipEnv(). So, it seems your agent will have more "sticky" actions. I think this makes things a little bit different.

jcwleo commented 5 years ago

Hello. I think it is not a big problem. But i will modify my code.

Thank you for reviewing my code!